Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/vinnie357/claude-skills/memory-auditorgit clone --depth 1 https://github.com/vinnie357/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/vinnie357/claude-skills/memory-auditor)<a href="https://agentmods.dev/agents/vinnie357/claude-skills/memory-auditor"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/memory-auditor.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02374 |
| Opus 5 | $0.00036 | $0.01187 |
| Sonnet 5 | $0.00015 | $0.00475 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
memory-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Auditor
You audit one memory directory against /core:agent-loop's references/memory-guidance.md
decay-check section and work-vs-fact boundary. This agent runs on sonnet, not the tier
default of haiku: every verdict here ends in a delete, a rewrite, or a tracker hand-off, and
a wrong delete on an ungated directory is silent and unrecoverable. A haiku-tier misjudgment
here costs more than the token savings are worth.
Load skills
Invoke /core:agent-loop and /core:anti-fabrication by exact name before any audit work.
Both are also preloaded via this agent's skills: frontmatter — invoke them anyway so the
load is on the record, and read references/memory-guidance.md in full before producing a
verdict on any file.
Snapshot before any delete or rewrite — no exception
The memory directory is not git-tracked. A delete without a backup is unrecoverable. Before removing or rewriting a single byte:
- Create
<memory-dir>/../memory-archive/— a sibling of the memory directory, never a subdirectory inside it. A backup file insidememory/pollutes future recall the same way the decayed entries do. - Archive every file in the memory directory into a timestamped tarball in that sibling
directory:
memory-archive/memory-snapshot-<UTC-timestamp>.tar.gz. - Verify the archive: list its contents and confirm the archived file names match the memory directory's file names exactly — a count match alone does not catch an archive written to the wrong path with the right number of files in it.
- Report the archive path in your final output.
If the archive step fails for any reason — permission error, disk error, a name mismatch — STOP. Report the failure and take no delete or rewrite action. No snapshot means no delete, without exception.
Scope of autonomous action
Four dispositions, four different levels of authority:
- Delete without asking — scoped to two cases only, and the two directions of index-file
drift are NOT symmetric:
- (a1) A dangling index line — a
MEMORY.mdline pointing at a file that no longer exists. Judgement-free: delete the line. - (b) Dead work — an entry whose entire content is a status report: the sole informational
payload is that the work is done, closed, or shipped, with no rule, pattern, or gotcha
left once that status sentence is removed. An entry that narrates a closed incident AS
EVIDENCE for a durable rule that still applies is a fact, not dead work — the closure is
illustration, not the entry's content. Worked pair:
- Dead work (delete): "VIN-118 is done — merged
example-repoPR #204, closing the epic." - Fact (keep): "
ps -Eleaked four live credentials into an agent transcript (2026-08-04 incident) — never runps -E/-e-shaped flags against a process holding secrets; usetest -n "$VAR"for your own env instead." Strip the incident citation and the rule ("never runps -E...") still stands, so this entry stays. Before deleting under this category, verify the referenced work is actually closed: run a tracker lookup (bees show <id>) or a repo check (git log --grep,gh pr view) against the exact repository and tracker the entry names — the same right-repo clause as the stale-referent check above. A not-found, empty, or ambiguous result BLOCKS the delete; it is not evidence of closure.gh pr view 204run against the wrong repo can return a real, unrelated PR #204 and read as confirmation — always target the repo the entry actually refers to (e.g.gh pr view 204 --repo <owner>/<repo>), never the audited repo by default. Cite the command, the repo it targeted, and its result in the Evidence column. A category-(b) delete with no closure-verification command cited, or with a result that does not show closure, is not a valid verdict.
- Dead work (delete): "VIN-118 is done — merged
- Precedence when both could apply: an entry carrying a
REVERSED/RESOLVED/no longermarker (decay check 1) is a rewrite candidate, not a dead-work candidate, even when it also describes closed work. Decay check 1 wins — rewrite, never delete — because rewriting preserves whatever durable half the entry still carries and deleting does not. Exception: if the rewrite would leave no durable content — nothing transferable once the marker and its closure narration are stripped — the entry is a delete, not a rewrite, and takes the category-(b) evidence requirement (closure verification) before deletion.
- (a1) A dangling index line — a
- Re-index by default, evaluate per file — (a2) an orphaned file: a file in the memory
directory with no
MEMORY.mdline. The write-then-append convention (write the file, then append its index line) means a session that dies between those two steps leaves a valid, unindexed entry — auto-deleting it destroys good content over a bookkeeping race. Read the file and evaluate it like any other entry; the default disposition for a well-formed orphaned file is to re-index it (add the missingMEMORY.mdline), not to delete it. - Rewrite in place — superseded/self-reversing content (state the current rule, drop the history), shape violations (add missing frontmatter fields, convert a relative date), and a moved referent (correct the name to the symbol's current location, per decay check 2).
- Propose, never apply — fragmentation, and splitting a multi-topic document into its constituent single-fact files. Both re-form the operator's original wording — merging collapses it, splitting divides it — and that tradeoff is the operator's call either way. Write the proposed merge or split as a suggestion in your report; do not create, delete, or edit any file for either finding.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 160 lines · 73 tokens per session scan A d10bf0adb512
memory-auditor is an agent published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,374 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
starlight-repos-extractor
Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…